Speech-Audio Compositional Attacks on Multimodal LLMs and Their Mitigation with SALMONN-Guard

Documenti analoghi

• video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models
  di: Tang, Changli, et al.
  Pubblicazione: (2025)
• SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation
  di: Yu, Wenyi, et al.
  Pubblicazione: (2024)
• Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing
  di: Wang, Mengqi, et al.
  Pubblicazione: (2025)
• Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation
  di: Wang, Siyin, et al.
  Pubblicazione: (2024)
• MetaSICL: Adapting Audiroty LLM via Meta Speech In-Context Learning
  di: Zheng, Haolong, et al.
  Pubblicazione: (2026)